SPEECH-TO-TEXT API

Accurate speech-to-text, at half the going rate.

Batch and streaming transcription through one OpenAI-compatible API. Proprietary and open-weight models behind a single integration, with speakers, entities and language-model processing available on the same request.

From $0.0012/min · Batch + streaming · Word-level timestamps
01 · OVERVIEW

What a speech-to-text API actually has to do.

Speech-to-text — also called automatic speech recognition, or ASR — converts spoken audio into written text. A production API has to do more than that: it has to return when each word was spoken, hold up on real-world audio with overlapping speakers and background noise, stay fast enough for the product it sits inside, and cost little enough that transcribing everything is affordable rather than a budget line you ration.

Most teams discover the gap after integrating. Transcription alone is rarely the product. You need to know who spoke, pull out names and dates, judge tone, and hand structured data to something downstream. That normally means a second vendor, a second integration and a second bill.

One request, the whole pipeline

Ultrafield exposes transcription as the first stage of a composable pipeline rather than a standalone endpoint. Diarization, speaker identification, transcript formatting, entity detection, sentiment and language-model processing attach to the same job. Stages are metered independently, so you pay for what a request runs and nothing else.

Economical without being slow or inaccurate

Being cheaper usually means a smaller model and worse output. We take a different route: run a lean inference stack, price per processed second rather than per seat or bundle, and let you choose the engine that fits each workload. Use hosted Whisper large-v3-turbo where latency matters, large-v3 where accuracy matters most, and Ultrafield ASR-1 where you want our own model on difficult audio. Faster token processing and lower latency ceilings are available on Pro and Enterprise, so scaling up buys speed rather than just a bigger invoice.

$0.07
per hour, batch
1 sec
billing granularity
3
speech models
6+
processing stages
02 · HOW IT WORKS

From audio to structured output.

01+
Send audio

Upload a file, pass a remote URL, or open a stream. One request shape covers all three.

POST /v1/audio/transcriptions
02PRO
Pick a model

Name the engine explicitly. Accuracy, latency and cost are yours to trade off, not ours to guess.

model: ultrafield-asr-1
03+
Add stages

Diarization, speaker ID, formatting, entities and sentiment run on the same job, not a second integration.

processing: [ ... ]
04+
Read structured output

Text, word-level timestamps, speaker turns and derived fields come back in one normalized response.

usage reported per response
03 · MODELS

Choose the engine. Keep the API.

MODELTYPEMODESBEST FOR
Ultrafield ASR-1PROPRIETARYBATCH + STREAMINGDifficult audio, max accuracy
Whisper large-v3-turboOPEN WEIGHTBATCH + STREAMINGLowest latency and cost
Whisper large-v3OPEN WEIGHTBATCHHigh accuracy, open weights
MODEL NAMED EXPLICITLY PER REQUEST · SWITCHING ENGINES DOES NOT CHANGE THE INTEGRATION
04 · RATES

Per processed minute.

MODELBATCHSTREAMING
Ultrafield ASR-1$0.0021/min$0.0031/min
Whisper large-v3-turbo$0.0012/min$0.0018/min
Whisper large-v3$0.0018/min·
Diarization$0.0010/min·
BILLED PER SECOND · SEE THE PRICING PAGE FOR PLANS AND VOLUME RATES
05 · USE CASES

Where teams put it to work.

01+
Contact center analytics

Transcribe and diarize large call archives, then extract entities and sentiment in the same pass.

BATCH · ASR-1 + DIARIZATION
02+
Meeting intelligence

Turn recordings into formatted, speaker-attributed transcripts and structured summaries.

BATCH · WHISPER V3 TURBO
03+
Live captions

Stream audio and render interim results immediately, finalizing segments as they settle.

STREAMING · FORMATTING
04SOON
Voice agents

Low-latency transcription in the loop of a conversational product, with interruption handling.

STREAMING · REALTIME
05+
Media and subtitling

Word-level timestamps for caption files, alignment and searchable archives.

BATCH · TIMESTAMPS
06+
Research and compliance

Long-form interviews and regulated recordings, with retention you control.

BATCH · SPEAKER ID
06 · FAQ

Questions, answered.

Q01

How much does the speech-to-text API cost?

Batch transcription starts at $0.0012 per minute ($0.07 per hour) on Whisper large-v3-turbo, and $0.0021 per minute ($0.13 per hour) on Ultrafield ASR-1. Streaming starts at $0.0018 per minute. You pay for the stages a request actually runs, billed per second with no minimums.

Q02

Which speech recognition models can I use?

Ultrafield ASR-1, our proprietary model, alongside open-weight Whisper large-v3 and large-v3-turbo. You name the model in the request, so switching engines never means switching integrations.

Q03

Does it support both batch and real-time transcription?

Yes. Uploaded files, remote audio URLs and low-latency streams share one API surface. Batch suits archives and analytics; streaming suits live captions and conversational products.

Q04

Is the API compatible with OpenAI?

The audio endpoints follow OpenAI conventions for routes, Bearer authentication, errors and usage reporting, so most clients need only a base URL and key change. Ultrafield-specific capabilities are added as extensions rather than by altering the compatible surface.

Q05

What languages are supported?

Language coverage follows the model you select. The Whisper family is multilingual across a broad set of languages; consult the models documentation for the current list and per-language guidance.

Q06

Do you train on customer audio?

No. We never train on customer audio, transcripts, derived content, voiceprints, prompts or outputs, and we do not route customer data to downstream services that may train on it.

Q07

How long is audio retained?

Source audio is removed within 24 hours of terminal processing, and derived result content is retained for 30 days by default. Operational and billing records are kept separately from customer content.

Q08

Can I get lower latency and higher throughput?

Yes. Pro raises concurrency to 50 batch jobs and 25 streams with priority job scheduling. Enterprise adds custom concurrency, throughput and rate limits, dedicated hosting and capacity planning for burst volume.

Get started

Give your product better ears.

Move from raw audio to accurate transcripts, speakers, entities, sentiment and application-ready output through one pipeline.

Batch and streaming · Proprietary and open models